Learning models with uniform performance via distributionally robust optimization Page 1 The
Annals of Statistics 2021, Vol. 49, No. 3, 1378–1406 https://doi.org/10.1214/20-AOS2004 © …

This monograph develops a comprehensive statistical learning framework that is robust to
(distributional) perturbations in the data using Distributionally Robust Optimization (DRO) …

Many decision problems in science, engineering, and economics are affected by uncertain
parameters whose distribution is only indirectly observable through samples. The goal of …

We develop an approach to risk minimization and stochastic optimization that provides a
convex surrogate for variance, allowing near-optimal and computationally efficient trading …

The goal of regression and classification methods in supervised learning is to minimize the
empirical risk, that is, the expectation of some loss function quantifying the prediction error …

Distributionally robust optimization (DRO) is a widely-used approach to learn models that
are robust against distribution shift. Compared with the standard optimization setting, the …

This paper proposes a distributionally robust approach to logistic regression. We use the
Wasserstein distance to construct a ball in the space of probability distributions centered at …

We obtain robust and computationally efficient estimators for learning several linear models
that achieve statistically optimal convergence rate under minimal distributional assumptions …

We develop efficient solution methods for a robust empirical risk minimization problem
designed to give calibrated confidence intervals on performance and provide optimal …

Consider supervised learning from iid samples {(y_i, x_i)} _ {i≤ n} where x_i∈ R_p are
feature vectors and y_i∈ R are labels. We study empirical risk minimization over a class of …